Moonshot · model
Kimi K2.7 Code benchmark scores
As of 2026-10-07, Kimi K2.7 Code (Moonshot) has measured scores on 19 benchmarks and estimated scores on 80 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 89.6% | measured |
| AA-HLE | 35.0% | measured |
| AA-SciCode | 47.8% | measured |
| Artificial Analysis Intelligence Index | 25.8% | measured |
| CritPt | 10.0% | measured |
| GDPval-AA | 27.0% | measured |
| GPQA Diamond | 89.2% | estimated ± 2.2 pp, high confidence |
| HLE | 43.8% | estimated ± 9.5 pp, medium confidence |
| IFBench | 63.2% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 79.3% | measured |
| LiveCodeBench v6 | 89.2% | estimated ± 3.1 pp, high confidence |
| AA-Omniscience Accuracy | 39.6% | measured |
| SciCode | 40.9% | estimated ± 2.9 pp, low confidence |
| Terminal-Bench 2.1 | 82.6% | estimated ± 6.9 pp, medium confidence |
| BrowseComp | 79.8% | estimated ± 8.4 pp, medium confidence |
| HLE w/ tools | 45.4% | estimated ± 6.1 pp, medium confidence |
| IFEval | 93.0% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, low confidence |
| VITA-Bench | 46.6% | estimated ± 9.9 pp, low confidence |
| τ²-bench results | 90.1% | measured |
| AA Coding Index | 60.8% | measured |
| APEX-Agents | 30.7% | estimated ± 0.6 pp, medium confidence |
| APEX-Agents-AA | 34.6% | estimated ± 5.7 pp, medium confidence |
| BioMysteryBench (human-difficult) | 40.7% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 85.8% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 76.3% | estimated ± 4.4 pp, high confidence |
| AutomationBench | 28.4% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 74.5% | estimated ± 2.6 pp, high confidence |
| CyberGym | 62.8% | estimated ± 5.3 pp, low confidence |
| JobBench | 46.4% | estimated ± 6.8 pp, medium confidence |
| SWE-bench Pro | 54.8% | estimated ± 4.5 pp, high confidence |
| τ³-bench results | 69.6% | estimated ± 1.8 pp, low confidence |
| WideResearch | 77.8% | estimated ± 9.1 pp, low confidence |
| AA Agentic Index | 22.5% | measured |
| MMLU-Pro | 85.7% | estimated ± 3.5 pp, high confidence |
| GPQA | 88.8% | estimated ± 3.2 pp, high confidence |
| AA-IFBench | 63.1% | measured |
| Gert Labs | 63.9% | estimated ± 8.2 pp, low confidence |
| AA-AnalystAgent | 19.1% | estimated ± 12.0 pp, low confidence |
| AA EnterpriseOps-Gym | 38.0% | estimated ± 3.6 pp, medium confidence |
| AA Harvey LAB | 82.2% | estimated ± 1.2 pp, medium confidence |
| ARC-AGI-1 | 77.1% | estimated ± 5.4 pp, medium confidence |
| ARC-AGI-2 | 37.0% | estimated ± 14.2 pp, low confidence |
| CursorBench 3.1 | 38.6% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 49.7% | measured |
| Terminal-Bench 3.0 | 10.6% | estimated ± 6.9 pp, low confidence |
| FrontierCode 1.1 Main | 33.0% | estimated ± 1.6 pp, low confidence |
| FrontierSWE v2 | 9.4% | estimated ± 9.5 pp, medium confidence |
| OSWorld-Verified | 69.7% | estimated ± 8.7 pp, low confidence |
| Vals GPQA Diamond | 88.0% | estimated ± 7.4 pp, medium confidence |
| Vals LiveCodeBench | 82.1% | measured |
| Vals MMLU-Pro | 86.8% | estimated ± 2.2 pp, high confidence |
| Vals SWE-bench | 78.2% | measured |
| Terminal-Bench 2.1 (Vals AI) | 67.0% | measured |
| VulcanBench v3 | 72.0% | estimated ± 5.1 pp, low confidence |
| AA AutomationBench | 4.5% | estimated ± 7.0 pp, medium confidence |
| GDP.pdf | 9.4% | estimated ± 5.4 pp, medium confidence |
| AA ITBench | 43.8% | estimated ± 3.6 pp, medium confidence |
| AA Tau3 Banking | 22.0% | estimated ± 5.8 pp, medium confidence |
| AA Terminal-Bench 2.1 | 82.9% | estimated ± 4.4 pp, high confidence |
| AA Terminal-Bench 4.0 | 21.6% | estimated ± 14.0 pp, low confidence |
| CursorBench 4.0 | 23.4% | estimated ± 1.6 pp, medium confidence |
| CWE-bench v1 | 37.0% | estimated ± 6.9 pp, low confidence |
| DeepSWE | 34.7% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 32.6% | estimated ± 5.7 pp, medium confidence |
| PostTrainBench v1.1 | 24.9% | estimated ± 2.7 pp, high confidence |
| ProgramBench | 53.6% | measured |
| Toolathlon-Verified | 51.5% | estimated ± 2.3 pp, low confidence |
| Vibe Code Bench | 34.7% | estimated ± 10.3 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 12.2 pp, low confidence |
| C-Eval | 93.1% | estimated ± 1.0 pp, medium confidence |
| Claw-Eval | 69.9% | estimated ± 5.7 pp, medium confidence |
| DeepPlanning | 48.2% | estimated ± 13.1 pp, low confidence |
| MCP Atlas | 76.0% | measured |
| MCP-Tasks | 77.0% | estimated ± 0.6 pp, low confidence |
| MMLU-Redux | 96.6% | estimated ± 1.1 pp, medium confidence |
| NL2Repo | 44.7% | estimated ± 4.7 pp, high confidence |
| QwenClawBench | 63.0% | estimated ± 2.6 pp, high confidence |
| SuperGPQA | 80.9% | estimated ± 7.5 pp, medium confidence |
| Terminal-Bench 2.0 | 71.5% | estimated ± 5.9 pp, medium confidence |
| Toolathlon | 50.1% | estimated ± 6.3 pp, medium confidence |
| HealthBench Hard | 19.6% | estimated ± 7.7 pp, low confidence |
| MMLU-Pro (Arcee) | 100.0% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 78.3% | estimated ± 2.4 pp, medium confidence |
| ResearchClawBench | 18.7% | estimated ± 1.8 pp, medium confidence |
| SWE-Rebench | 58.1% | estimated ± 8.9 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 83.3% | estimated ± 0.6 pp, low confidence |
| DRACO | 72.6% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 55.1% | estimated ± 1.6 pp, low confidence |
| HealthBench (raw) | 44.3% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 57.7% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 55.0% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 16.6% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 76.4% | estimated ± 1.8 pp, low confidence |
| LiveCodeBench | 100.0% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 52.1% | measured |
| MMLU | 93.3% | estimated ± 1.1 pp, low confidence |